1 / 20

EECS 750: Advanced Operating Systems

EECS 750: Advanced Operating Systems. 01/22/2014 Heechul Yun. About Instructor. Assistant Prof., Dept. of EECS, University of Kansas (Aug.’13 ~ ) Office: 3040 Eaton , 236 Nichols Email : heechul.yun@ku.edu Educations Ph.D. (CS), University of Illinois at Urbana-Champaign

navid
Download Presentation

EECS 750: Advanced Operating Systems

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. EECS 750: Advanced Operating Systems 01/22/2014 Heechul Yun

  2. About Instructor • Assistant Prof., Dept. of EECS, University of Kansas (Aug.’13 ~ ) • Office: 3040 Eaton, 236 Nichols • Email: heechul.yun@ku.edu • Educations • Ph.D. (CS), University of Illinois at Urbana-Champaign • M.S. (CS) and B.S (CS), KAIST • Research Areas • Operating systems, embedded/real-time systems • More Information • http://ittc.ku.edu/~heechul

  3. About This Class • Lecture: M/W/F 3:00 – 3:50 LEA 2115 • Office hour: M/F 4:00 - 5:00 @ 3040 Eaton • Advanced topics in OS and system software • Prerequisite: Undergraduate OS • No textbook ! • Optional: Linux Kernel Development (3rd edition)by Robert Rove • Lecture slides and papers • Seminar style: I and YOU will present (more on later) • Course website: http://ittc.ku.edu/~heechul/courses/eecs750/S14 • Audience: Grad students (senior undergraduate) who are interested in research

  4. About This Class • Goals • Learn advanced topics in operating systems • Improve your research skills • A research cycle • Read papers • Discuss papers with advisors and peers • Write a paper • Present your ideas at a conference

  5. Operating System • What are operating systems? • Provide abstractions • Easy to use (hide details), functionality • E.g., filesystem, process (virtual memory), … • Manage resources • Performance, efficiency • E.g., CPU scheduling, I/O scheduling,…

  6. Topics • Performance • How to manage Multicore, cache, DRAM, SSD, and GPU for good throughput/fairness/QoS? • Power/Energy • How to save power/energy while still getting enough performance? • Reliability • How to make system more predictable, less buggy? • If you have bugs, how to find them, automatically?

  7. Reading Papers • Normally, each class will cover 1 paper • 3 papers/week • Reading paper well is an important skill • A good reference: “How to Read a Paper” • You are required to write a summary and e-mail me by 11:59 p.m. the day before the class • You can skip one paper of your choice/week

  8. Written Summary • Must be in ASCII text format (no words, pdf) • Include “[EECS750]” in the subject line • Each summary should include: • Summary of main ideas • What you liked • What you disliked

  9. Written Summary: Example • [Summary] This paper presents a kernel level page allocator which is DRAM Bank-Aware. This allocator is able to allocate pages across cores in a way that causes banks to be shared or partitioned depending on user configuration. This can be used to provide more predictable memory access to multicore software. The authors implemented their memory allocator in a recent version of the Linux Kernel and compared its performance with the existing buddy allocator. • [The good] This paper is well written. The issue of DRAM banks was not familiar to me at the time of reading but was well explained which motivated the rest of the paper well. The algorithm used is quite straightforward and the explanation is easy to follow. • [The bad] While the authors acknowledge that the approach they take bears similarity to multi-core page coloring[1,2,3,4] the novelty of their work is not well established.  This work appears to be a relatively straightforward application of rudimentary page coloring techniques. The related work section touches on these similarities but does not establish any particular novelty aside from the fact that this paper is addressing the problem of shared DRAM banks for the sake of isolation and not shared caches.

  10. Lecture Organization • Three phases • I will Introduce the paper • Lecture about the topic, background, and Linux kernel • YOU (or I) will present the paper • We will discuss the paper • Each student is required to present two papers per semester • May change depending on the class size

  11. Reading List • Posted on the class website • Subject to change • Mostly recent papers and some classic ones • Sign-up process • Email me two papers in the list you want to present • I will update the schedule on a First Come First Serve basis

  12. Paper Presentation & Discussion • Suggested structure (20-30min) • Motivation & Background • Ask why the authors write this paper? • Explain the main ideas • From your perspective. Careful about their assumptions • Discussion topics • Like/dislikes • What can you do differently? • Send your slides (draft) to me by 5:00 p.m. the day before your presentation

  13. Project • A team work • Ideally two; up to three is okay. • A good project • A publishable research project • E.g., “I have an idea to save power consumption of a mobile device by considering not only CPU, but also memory clock speed. • http://www.ittc.ku.edu/~heechul/papers/multidvfs-ecrts10.pdf • A re-implementation/validation of a published paper • E.g., “I will re-implement Kendo (ASPLOS’09) on my Linux machine using some new fancy library” • https://code.google.com/p/dpthread/wiki/README • A comprehensive evaluation of certain system behaviors • E.g., “I want to know when my smartphone’s battery drains fast” • Any (useful) system software with substantial implementation effort • E.g., “I want to build a my own malloc library and compare its performance with the standard malloc library.”

  14. Project Ideas • Some ideas will be posted on the class website • Your own idea is the best • Feel free to discuss with me • Try to tie your project to your field of research • E.g., if you are doing architecture research, then try something OS related in your research

  15. Project Schedule • Feb. 3: Email me about your group • Member names • Feb. 15: Proposal due • 1 page: include what you will build/evaluate • Apr. 2: Midterm progress report due • 3 pages: include intro, related work, progress and plan • May.2 (3h): Project presentation • No class on Apr. 28 and 30 • May. 16: Final report due • 5~8 pages: include results and conclusion • a complete paper in two-column IEEE/ACM format

  16. Latex • Everybody in CS uses it to write papers • Proposal/midterm/final report should be written with Latex • Paper template is on the course website • Ubuntu • $ sudo apt-get installtexlive-full • Window • Install MikTex. • Google “latex editor”

  17. No Exams !!!

  18. Grading • Class participation (10%) • Paper summaries (20%) • Student presentations (20%) • Project (50%) • Proposal: 5% • Midterm report: 10% • Final presentation: 15% • Final report: 20%

  19. Office Hours • M/F 4:00 – 5:00 at 3040 Eaton • By appoint at 236 Nichols • heechul.yun@ku.com

  20. Introduce Yourselves • Name • Status: grad/undergrad, year • Relevant background • Research interests

More Related